annahdo / implementing_activation_steeringLinks
A collection of different ways to implement accessing and modifying internal model activations for LLMs
☆19Updated last year
Alternatives and similar repositories for implementing_activation_steering
Users that are interested in implementing_activation_steering are comparing it to the libraries listed below
Sorting:
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆126Updated 8 months ago
- Experiments with representation engineering☆13Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆98Updated 2 years ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆222Updated 10 months ago
- ☆36Updated last year
- Erasing concepts from neural representations with provable guarantees☆238Updated 9 months ago
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- Algebraic value editing in pretrained language models☆66Updated last year
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆19Updated this week
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated 2 weeks ago
- ☆74Updated 2 weeks ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆94Updated 2 years ago
- ☆128Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆219Updated last week
- Steering Llama 2 with Contrastive Activation Addition☆188Updated last year
- ☆30Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Updated 9 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆25Updated 11 months ago
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- Measuring the situational awareness of language models☆38Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆15Updated last month
- ☆126Updated last year
- ☆29Updated last year
- Utilities for the HuggingFace transformers library☆72Updated 2 years ago
- ☆247Updated last year
- ☆191Updated last week